NVIDIA: Llama 3.1 Nemotron Ultra 253B v1✓ Catalog verified
Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100 node. Note: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see Usage Recommendations for more.
Overview
Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100 node. Note: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see Usage Recommendations for more.
Access: available through the official Nvidia API. Context window: 131K.
Specifications
| API identifier | nvidia/llama-3.1-nemotron-ultra-253b-v1 |
| Provider | Nvidia |
| Model type | Text LLM |
| Context window | 131K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | Apr 8, 2025 |
| Tokenizer | Llama3 |
| Moderated | No |
| Architecture modality | text->text |
API defaults
{
"top_k": null,
"top_p": null,
"temperature": null,
"presence_penalty": null,
"frequency_penalty": null,
"repetition_penalty": null
}Pricing
Live pricing components for nvidia/llama-3.1-nemotron-ultra-253b-v1 as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $6e-7 | $0.60 / 1M | Per input token |
| Completion tokens | $0.0000018 | $1.80 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.66Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | Not advertised | Supports tools / function calling |
| Self-Hosting | Not advertised | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="nvidia/llama-3.1-nemotron-ultra-253b-v1",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| AionLabs: Aion-1.0 | Aion Labs | 131K | $4.00 | View → |
| AionLabs: Aion-1.0-Mini | Aion Labs | 131K | $0.70 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 cost?
$0.60 per 1M input tokens and $1.80 per 1M output tokens on the official Nvidia API.
What is the context window of NVIDIA: Llama 3.1 Nemotron Ultra 253B v1?
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 supports up to 131K tokens of context.
Does NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 support tool / function calling?
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.
How do I access NVIDIA: Llama 3.1 Nemotron Ultra 253B v1?
Use the official Nvidia API with the model id `nvidia/llama-3.1-nemotron-ultra-253b-v1`. See the Quick start section above for code examples.